© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59280
    Prev
    Next
    INDEX
    Explanations

    X out of Y counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĮÑİ
    -0.10
    ither
    -0.10
    ä¸ĭçıŃ
    -0.09
    æĪĸå°Ĩ
    -0.08
    lig
    -0.08
    æĺ¥é£İ
    -0.08
    çľĭçĶµå½±
    -0.08
    ople
    -0.08
    inha
    -0.08
     Pey
    -0.08
    POSITIVE LOGITS
    ä¼Ĺ
    0.10
    ä¸Ģåı£æ°Ķ
    0.10
    èĩªæľī
    0.09
    çľ¾
    0.09
    æľ¬èĥ½
    0.09
    ç¥ī
    0.09
    ä¼ĹæīĢ
    0.08
    éĩįä¸Ń
    0.08
    游æĪıå½ĵä¸Ń
    0.08
    ç¾ļ
    0.08
    Activations Density 0.014%

    No Known Activations